Turn an HBR article into a strategic plan.

What the AI will do

• Do the work you rarely have time for after reading a provocative article: extract its method, apply it to your current projects and write a practical plan.
• Search your emails, chats, project records and strategy documents for specific places the idea could help.
• Develop the selected application into a concrete plan, have an independent critic challenge it and revise it.

What you can provide

• An article, URL, pasted text or readable file—from HBR or any other useful source.
• Any project you already have in mind; accessible work records can help the AI discover an application.

Where you'll take part

• Choose the application worth developing and settle decisions the work record cannot answer.
• Review substantive changes if the criticism calls for a different direction.

What you'll get

A practical strategic plan tailored to your work, with concrete actions, measures, necessary decisions and the strongest remaining objection.

Activity context

You read something interesting or provocative—in HBR, a blog post or somewhere else—and think, “We should try that.” But who has time to extract the method, work out how it applies and turn it into a plan?

Drop the article or its URL into an LLM. Let it do the hard work of applying the idea to your actual projects, people and circumstances. A separate critic can test whether the idea survives contact with your business.

For the user

Give the AI the article or link and whatever sparked your interest. You do not need to prepare a summary or framework. It will investigate your working context, propose a useful application and carry the chosen idea through a complete, challenged plan.

Guidance for the AI

These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.

Start with the activity and the user's context

Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.

Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.

Check the capabilities needed for this work

Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.

When useful access is missing:

• Explain what you cannot reach and how that material would help.
• Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
• If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
• Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.

Ask focused questions and respect the answers

Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.

Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.

Keep evidence and independent contributions distinct

Distinguish evidence, inference, and missing information. Check your work against the source material.

Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:

• Give each agent a bounded brief and the context appropriate to its role.
• Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
• Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.

Produce, check, and revise the result

Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.

Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.

Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.

Your AI prompt

Help me turn an interesting article into a practical strategic plan for my own work. The source may be HBR, a blog post or another publication. Read it, extract the substantive method, discover how it could apply to my actual situation, and develop and independently challenge a complete plan. Carry the research and drafting; do not ask me to write a framework first.

Read the actual article

Open the supplied URL or read the text or file. Retrieve the full relevant article through available permitted access, including important figures and qualifications. If it is inaccessible or only a preview is available, ask for its text or a usable copy and explain what is missing. Do not infer its complete argument from the headline, search snippets or summaries. Continue independent context discovery while waiting, without claiming to have read the article.

Identify the author, publication date, central claim, proposed mechanism, actual examples, evidence, conditions and limits. Distinguish a documented result from the author's advice and your interpretation. Follow pivotal factual claims to original sources where available, especially if their truth or current relevance would change the proposed application. Keep quotations short and preserve links; do not reproduce the article as the deliverable.

Extract the actual method in plain language: what someone would do, in what order, with what inputs, and why the author expects it to work. If the article is a provocative idea rather than an executable method, say so and label the operational steps you develop as your proposed adaptation. Do not invent a named framework and attribute it to the author.

Discover where it could matter in my work

Inspect and try available connections. Search emails, chats including WhatsApp where accessible, calendar-linked meetings and transcripts, current project documents, strategy and planning files, customer or operating data, earlier experiments and decision records. Start with topics from the article and my initial interest, then follow concrete projects, people and issues found in the record.

Look for a current need the idea could address, work already underway, a prior attempt that succeeded or failed, relevant constraints, commitments and measures of success. Establish the intended decision makers, people doing the work and people affected through actual roles, correspondence and recorded concerns. Keep evidence of their preferences separate from a predicted reaction.

Try supported access and export routes before asking me to gather material. If context remains thin, ask one focused question about the specific project or constraint that would make the application useful. Rough notes are welcome; mark a plan based on them as provisional where it depends on missing company evidence. Do not investigate the entire organization when one well-chosen project provides the needed context.

Choose the application with me

Present a few concrete applications grounded in what you found, unless I already chose one. For each, explain the problem or opportunity, the part of the article being applied, what would change in practice, the evidence of fit and the most consequential unknown. Include a small example of what the activity or result would look like.

Recommend an application when supported and let me choose, reject the suggestions or supply another. Ask the most useful unresolved question one at a time. Confirm a consequential interpretation you supply on my behalf before relying on it. If the article is a poor fit, explain the specific mismatch and explore whether a smaller part is useful rather than force a complete plan from it.

Build the concrete strategic plan

For the chosen application, identify the outcome, baseline and measure of success using actual business definitions where possible. Translate the article's mechanism into work suited to this setting, accounting for scale, incentives, customers, capabilities and decision rights. Preserve what the original idea requires; explain any material adaptation and its rationale.

Write a complete plan that shows:

• The result sought and why this idea might help here.
• The actual changes in work, illustrated by a before-and-after example.
• The sequence of actions, dependencies and decision points.
• Existing roles that could own the work and commitments still needing confirmation.
• Required inputs, capabilities, time and resources, with estimates distinguished from confirmed facts.
• A first useful test or implementation slice and what it must produce.
• Measures and review moments that would show whether to continue, adapt or stop.

Do the supporting work the plan needs: analyze available data, draft the relevant brief, template, sample customer interaction or first work product, and develop ready-to-use test materials. Choose artifacts that make this particular application tangible rather than attaching a generic checklist. The plan should be usable without another person first translating broad verbs into tasks.

Use bounded agents when the project warrants separate evidence, feasibility or audience investigations. Brief each with the chosen application, actual sources, question, deliverable and completion criteria. Maintain coverage, use waves as needed and reconcile conflicting findings before dependent planning. Without agents, use manageable passes or fresh-session handoffs; do not claim independence for shared-context work.

Have an independent critic challenge the actual plan

Give a fresh reviewer the article, full plan, relevant company evidence and the agreed objective, without your explanation of why the plan is good. Ask it to test whether the application reflects the article, whether the mechanism plausibly transfers, whether company evidence supports the fit, and whether the actions and measures test the promised result. Have it identify the strongest reason the organization should decline the plan as well as what stands up.

Use specialist criticism where the plan contains a consequential claim requiring that expertise, checking current authoritative sources as appropriate. If independent review is unavailable, prepare a fresh-session brief or perform a clearly identified separate pass. Do not replace source checking with a vote among agents.

Investigate material objections, revise the full plan and recheck the affected portions. Return a substantive change of goal, commitment or recommended strategy to me for a decision; continue independent repairs while waiting. Preserve an unresolved objection if the evidence cannot settle it.

Deliver the plan and its first usable materials

Lead with the actual application and what the plan would change. Deliver the revised plan, useful first artifacts, sources and a concise account of the strongest surviving objection and the evidence that could resolve it. Distinguish the article's claims, our adaptation and what remains untested. Keep technical production details out of the human explanation unless they affect a decision.

Stop after the finished plan and materials. Do not launch the initiative, assign colleagues work, send messages or represent the plan as adopted merely because it is written. Invite corrections to the actual artifact and incorporate them within the agreed scope.

Done when

You have a complete, challenged plan that applies the article to a real part of your work, with the first useful materials ready and untested assumptions visible.

These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.